Analysis and Forecasting of Crude Oil Price Based on Univariate and Multivariate Time Series Approaches

Abstract

This paper discusses the notion of multivariate and univariate analysis for the prediction of crude oil price in India. The study also looks at the long-term relationship between the crude oil prices and its petroleum products price such as diesel, gasoline, and natural gas in India. Both univariate and multivariate time series analyses are used to predict the relationship between crude oil price and other petroleum products. The Johansen cointegration test, Engle–Granger test, vector error correction (VEC) model, and vector auto regressive (VAR) model are used in this study to assess the long- and short-run dynamics between crude oil prices and other petroleum products. Prediction of crude oil price has also been modeled with respect to the univariate time series models such as autoregressive integrated moving average (ARIMA) model, Holt exponential smoothing, and generalized autoregressive conditional heteroskedasticity (GARCH). The cointegration test indicated that diesel prices and crude oil prices have a long-run link. The Granger causality test revealed a bidirectional relationship between the price of diesel and the price of gasoline, as well as a unidirectional association between the price of diesel and the price of crude oil. Based on in-sample forecasts, accuracy metrics such as root mean square logarithmic error (RMSLE), mean absolute percentage error (MAPE), and mean absolute square error (MASE) were derived, and it was discovered that VECM and ARIMA models can efficiently predict crude oil prices.